Open Models, Ready for Production

Mistral-7B-Instruct-v0.2-4b-r32-task099

Qwen3-4B-Instruct-2507

sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed1

dpo_chatbot_arena_llama-3.1-8b_as_nemotron-nano-30b-a3b_seed1

sft_chatbot_arena_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed1

cnk12_GRPO_KL_Qwen2.5-3B-Instruct_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL

sft_gsm8k_gpt-oss-20b_as_qwen3.6-27b_seed3

gemma2-9b-it-biology-pgd-s0.50

dpo_gsm8k_gpt-oss-20b_as_llama-3.1-8b_seed3

dpo_gsm8k_gpt-oss-20b_as_nemotron-nano-30b-a3b_seed2

gemma2-9b-it-biology-pgd-s0.0

gemma2-9b-it-biology-pgd-s0.40

gpt2-large-dpo-openrouter

Mistral-7B-Instruct-v0.2-4b-r8-task081

DeepSeek-V3.2

dpo_gsm8k_llama-3.1-8b_as_nemotron-nano-30b-a3b_seed1

deepseek_r1_finetune_16bit

sft_chatbot_arena_nemotron-nano-30b-a3b_as_gpt-oss-20b_seed1

bias-ant-ect-seed42

bias-ant-ect-seed123

dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed1

dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-20b_seed3

dpo_writingprompts_llama-3.1-8b_as_nemotron-nano-30b-a3b_seed2

sft_chatbot_arena_llama-3.1-8b_as_nemotron-nano-30b-a3b_seed3

sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed2

Qwen3-14B-Abliterated

whisper-v3-ft-uganda-12lang

sft_writingprompts_gpt-oss-20b_as_qwen3.6-27b_seed2

energy-exp1-dpo-offline

sft_gsm8k_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1

devpost-hacks-qwen3-4b-judge

sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed2

Mistral-7B-Instruct-v0.2-4b-r64-task044

hanifabdlh

mistral-7b-instruct-v0.3-lora-id-custom

sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed3

Mistral-7B-Instruct-v0.2-4b-r128-task076

kirk-tung

tiny-llama-cpsc254

DeepSeek-V4-Pro

cve-cwe-qwen3-32b

sft_writingprompts_gpt-oss-20b_as_nemotron-nano-30b-a3b_seed1

Aram_Protea_14B